Traffic Safety System Research Articles

Using deep learning model integration to build a smart railway traffic safety monitoring system

According to the importance of railway safety, it is crucial to build a smart railway traffic safety system in Taiwan, especially there are often to see related accidents. Therefore, this study aimed to build a smart railway traffic safety system using the integration of object detection, segmentation, machine learning, and notification system. First, the Mask R-CNN model was applied to automatically build the digital boundaries of railway, which achieved an average Interest of Union (IOU) of over 0.9. Then, the YOLO v3 model was applied to detect intrusions of railway, especially humans’ intrusion. The above object detection model achieved an Overall accuracy (OA) of over 90% for different classes, and an OA of 95.68% for human detection. The YOLO v3 model was also able to detect intrusion within different scenarios, such as nighttime, rainy daytime, and rainy nighttime. Moreover, the XGBoost model was applied to predict the sizes of intruding objects, which has a low MAE of 0.54 cm and an R2 score of 0.997. Finally, the LINE bot was applied to notify the related operators, including the above information, such as time of intrusion, locations, classes of intruding objects, sizes and the image of intrusion. The above implementation can be helpful for railway traffic safety monitoring, which may help related accidents prevention.

Aggressive Driving Behavior Recognition based on K-means Clustering

Accurate identification of aggressive driving behavior is crucial for improving traffic safety and promoting social responsibility, and it is also a key component in the realization of intelligent transportation systems. This paper proposes a method for aggressive driving behavior recognition and data modeling based on K-means clustering. First, the NGSIM (Next Generation Simulation) vehicle trajectory dataset is used for preprocessing the raw data, and effective behavioral feature representations are obtained through feature extraction. Next, Principal Component Analysis (PCA) is applied to reduce the dimensionality of the data, extracting three main components to simplify the data structure. Subsequently, the K-means clustering algorithm is employed to classify the reduced data and identify potential patterns of aggressive driving behavior. Experimental results demonstrate that the proposed method effectively identifies aggressive driving behavior, providing technical support for improving traffic system safety and raising awareness of social responsibility.

Ship visual trajectory exploitation via an ensemble instance segmentation framework

Maritime traffic safety is of utmost importance in the shipping industry. It is common to avoid potential traffic accident via the support of varied kinematic maritime data (e.g., ship position, ship speed). The study aims to fulfill maritime traffic safety enhancement by extracting multiple ship trajectories from maritime video data. The proposed framework is implemented with three steps. Firstly, the framework obtains initial ship imaging positions by proposing an ensemble YOLOX (You Only Look Once X) with CenterNet model. Secondly, ship contours from each maritime frame are explored with the deep snake module. Thirdly, consecutive ship imaging trajectory is identified with an enhanced Bytetrack multi-ship target tracking algorithm. Experimental results demonstrate that our model outperforms other ship trajectory extraction-like models considering that the identification F-Score (IDF1), IDP (identification Precision), IDR (identification recall), and MOTA (multi-object tracking accuracy) for our proposed framework were 0.965, 0.995, 0.933, and 0.925, respectively. The research findings can help ship crew better aware on-site traffic situations, and thus make optimal ship maneuvering operations for the purpose of enhancing maritime traffic system safety and sustainability.

Developing a Machine-Learning-Based Automatic Incident Detection System for Traffic Safety: Promises and Limitations

Developing a Machine-Learning-Based Automatic Incident Detection System for Traffic Safety: Promises and Limitations

Vehicle-Pedestrian near miss analysis at signalized mid-block crossings

Introduction: This study aims to identify the factors related to pedestrian and roadway characteristics that affect vehicle–pedestrian Post Encroachment Time (PET) and Relative Time to Collision (RTTC) under traffic control systems at mid-block pedestrian crossings. Methodology: A total of 112 h of video data were collected using multiple cameras from Pedestrian Hybrid Beacon (PHB) and Rectangular Rapid Flashing Beacon (RRFB) sites. To extract vehicle and pedestrian trajectories and construct an accurate dataset, where each observation corresponds to a specific timeframe, with a recorded speeds of both vehicles and pedestrians, a self-developed cutting-edge Computer Vision (CV) technology was deployed. A bivariate regression approach is employed to capture the relationship between near misses and various factors. Results and Conclusions: The findings reveal that both pedestrian and roadway characteristics significantly influence PET and RTTC. Pedestrian characteristics, such as gender, clothing color, distraction, waiting time, and crossing speed, significantly affect both PET and RTTC. The presence of children as pedestrians, eye contact with drivers, and pedestrian signal compliance rate has a significant influence on PET. Among roadway characteristics, the presence of a median, hourly traffic flow, and land use diversity of the crossing area were found to be significant determinants of both PET and RTTC. The results indicate that there is no difference in the influence of RRFB and PHB on PET values, but there is a significant difference in the influence of RRFB and PHB on RTTC values. PHB increases RTTC relative to RRFB. Finally, this study enriches existing literature by incorporating unique factors that impact pedestrian safety. Practical Applications: The findings underscore the importance of data-driven approach to pedestrian safety, encouraging transportation agencies to implement targeted and effective safety strategies. In the future, the integration of artificial intelligence (AI) in traffic management and safety systems could greatly benefit from incorporating these findings.

On estimating the size of informative fragments in the sea surface images

The paper proposes a solution to one of the problems arising in the construction of modern traffic safety systems in marine areas, namely, estimating the size of informative fragments in the image, which it seems advisable to use when detecting foreign objects on the sea surface image. It is proposed to estimate the size of informative fragments based on calculating the average distance between the contours of the wave elements visible in the image, such as their crests, depressions, etc. The contours of these wave elements are determined based on the Canny operator. The estimation of the sizes of informative fragments is performed along the columns and rows of the analyzed image. Computational experiments have been carried out to illustrate the developed algorithm efficiency. The obtained estimates of the sizes of informative fragments of sea surface images seem appropriate to use in their analysis, in particular, when solving problems of detecting foreign objects on sea surface images.

Short-term traffic flow prediction based on weather factors analysis and neural network

With the progress of urban transportation infrastructure and the construction of intelligent transportation system, sufficiently accurate traffic flow prediction is of increasing importance for urban planning and management. This paper based on traffic flow data in a section of highway in Los Angeles, USA, we combine external qualitative data such as weather and work calendars, analyze and process the factors significantly influencing traffic flow first, then train and test the traffic flow data by building machine learning Support Vector Regression (SVR) model and the Back Propagation neural network (BP neural network). The test results show that the BP neural network traffic flow prediction model incorporating the external environment is more accurate, and that the external environment has a significant impact on the traffic flow prediction problem. If more significantly influencing factors can be taken into account, or if the current algorithm can be optimized, the prediction accuracy will have further improved, thus effectively enhancing the efficiency and safety of traffic systems.

Алгоритмы управления карьерным самосвалом при проскальзывании колес

Mine dump trucks with a carrying capacity of 90 tons or more are equipped with an electromechanical transmission that controls the traction motors of the driving wheels. Due to unfavorable operation conditions of dump trucks, there are strict requirements to the driving safety along unpaved roads of open pits. The results of BELAZ dump trucks tests and authors maintenance experience have shown that the active security system is especially needed and gives essential assistance to a driver. Loss of control of а loaded truck, for example, during sharp braking on a slippery icy road, can lead to а serious accident and additional costs for repairing mining equipment. Thus, the development of traffic safety systems of mine dump trucks with electromechanical transmission is an important task. The methods of automatic control, mathematical modeling and numerical solution of differential equations are used to develop control algorithms for a mine dump truck. To test the proposed solutions, the method of full-scale experiment is used in real-life driving conditions along the dirt and icy roads. Control algorithms that use data of additional front (driven) wheels sensor are proposed. The results of tests of a BELAZ dump truck with a carrying capacity of 90 tons are presented. The results confirm the effectiveness of the developed control system in comparison with the one currently used in stock-produced items. The developed ABS system with speed sensors of the front wheels of a dump truck has proved the braking effectiveness along a slippery road. It makes it possible to improve the controllability of the dump truck significantly under conditions of lack of road adhesion, preventing the dump truck from skidding and wheels blocking. And it makes it possible to reduce mechanical effects on the transmission and anti-slip system sensitivity to different traffic conditions. The adaptive system remains operational if one of the front wheel sensors fails and if compared to the standard system it works equally effectively in various traffic conditions. The implementation of the obtained results will improve traffic safety and reduce the accident rate of expensive mining equipment.

Remote sensing traffic scene retrieval based on learning control algorithm for robot multimodal sensing information fusion and human-machine interaction and collaboration.

In light of advancing socio-economic development and urban infrastructure, urban traffic congestion and accidents have become pressing issues. High-resolution remote sensing images are crucial for supporting urban geographic information systems (GIS), road planning, and vehicle navigation. Additionally, the emergence of robotics presents new possibilities for traffic management and road safety. This study introduces an innovative approach that combines attention mechanisms and robotic multimodal information fusion for retrieving traffic scenes from remote sensing images. Attention mechanisms focus on specific road and traffic features, reducing computation and enhancing detail capture. Graph neural algorithms improve scene retrieval accuracy. To achieve efficient traffic scene retrieval, a robot equipped with advanced sensing technology autonomously navigates urban environments, capturing high-accuracy, wide-coverage images. This facilitates comprehensive traffic databases and real-time traffic information retrieval for precise traffic management. Extensive experiments on large-scale remote sensing datasets demonstrate the feasibility and effectiveness of this approach. The integration of attention mechanisms, graph neural algorithms, and robotic multimodal information fusion enhances traffic scene retrieval, promising improved information extraction accuracy for more effective traffic management, road safety, and intelligent transportation systems. In conclusion, this interdisciplinary approach, combining attention mechanisms, graph neural algorithms, and robotic technology, represents significant progress in traffic scene retrieval from remote sensing images, with potential applications in traffic management, road safety, and urban planning.

Evaluating the effectiveness of machine learning techniques in forecasting the severity of traffic accidents

Traffic accidents pose a significant public safety concern, leading to numerous injuries and fatalities worldwide. Predicting the severity of these accidents is crucial for developing effective road safety measures and reducing casualties. This paper proposes an analytic framework that utilizes machine learning models, including Naive Bayes, Random Forest, Logistic Regression, and Artificial Neural Networks, to predict the severity of traffic accidents based on contributing factors. This study analyzed ten years of UK traffic accident data (2005–2014, N = 2,047,256) to develop and compare different ML models. Results show that the proposed Random Forest and Logistic Regression models achieved an 87% overall prediction accuracy, outperforming Naive Bayes (80%) and Artificial Neural Networks (80%). By employing Random Forest-based feature importance analysis, the study identified Engine Capacity, Age of the vehicle, make of vehicle, Age of the driver, vehicle manoeuvre, daytime, and 1st road class as the most sensitive variables influencing traffic accident severity prediction. Additionally, the suggested RF model outperformed most existing models, attaining a remarkable overall accuracy and superior predictive performance across various injury severity classes. The findings have significant implications for developing efficient road safety measures and enhancing the current traffic safety system. The proposed framework and models can be adapted to various datasets to achieve accurate and effective predictions of traffic accident severity, serving as a valuable reference for implementing traffic accident management and control measures. Future research could extend the proposed framework to datasets containing Casualty Accident information to further improve the accuracy of injury severity prediction.

State of Bicycle Modeling in SUMO

Microscopic traffic simulation tools provide ever-increasing value in the design and implementation of motor vehicle transport systems. Research and development of automated and intelligent technologies have highlighted the usefulness of simulation tools and development efforts have accelerated in recent years. However, the majority of traffic simulation software is developed with a focus on motor vehicle traffic and has limited capabilities in the simulation of bicycles and other micro-mobility modes. Bicycles, e-bikes and cargo bikes represent a non-negligible modal share in many urban areas and their impact on the operation, efficiency and safety of traffic systems must be considered in any comprehensive study. The Differentiation between different types of micro-mobility modes, including microcars, e-kick scooters, different types of bicycles and other personal mobility devices, has not yet attracted enough attention in the development of simulation software which creates difficulties in including these modes in simulation-based studies. On November 25th, 2022, members of the SUMO team at DLR organized a workshop to assess the state of bicycle simulation in SUMO, identify shortcomings and missing capabilities and prioritize the order in which bicycle traffic related features should be modified or implemented in the future. In this paper, different aspects of simulating bicycle traffic in SUMO are examined and an overview of the results of the workshop discussions is given. Some suggestions for the future development of SUMO emerging from this workshop, are presented as a conclusion.

Achieving realistic cyclist behavior in SUMO using the SimRa dataset

Increasing the modal share of bicycle traffic to reduce carbon emissions, reduce urban car traffic, and to improve the health of citizens, requires a shift away from car-centric city planning. For this, traffic planners often rely on simulation tools such as SUMO which allow them to study the effects of construction changes before implementing them. Similarly, studies of vulnerable road users, here cyclists, also use such models to assess the performance of communication-based road traffic safety systems. The cyclist model in SUMO, however, is very imprecise as SUMO cyclists behave either like slow cars or fast pedestrians, thus, casting doubt on simulation results for bicycle traffic. In this paper, we analyze acceleration, deceleration, velocity, and intersection left-turn behavior of cyclists in a large dataset of real world cycle tracks. We use the results to improve the existing cyclist model in SUMO and add three more detailed cyclist models and implement them in SUMO.

Injury-Based Surrogate Resilience Measure: Assessing the Post-Crash Traffic Resilience of the Urban Roadway Tunnels

Crash injuries not only result in huge property damages, physical distress, and loss of lives, but arouse a reduction in roadway capacity and delay the recovery progress of traffic to normality. To assess the resilience of post-crash tunnel traffic, two novel concepts, i.e., surrogate resilience measure (SRM) and injury-based resilience (IR), were proposed in this study. As a special kind of semi-closed infrastructure, urban tunnels are more vulnerable to traffic crashes and injuries than regular roadways. To assess the IR of the post-crash roadway tunnel traffic system, an over-one-year accident dataset comprising 8621 crashes in urban roadway tunnels in Shanghai, China was utilized. A total of 34 variables from 11 factors were selected to establish the IR assessment indicator system. Methodologically, to tackle the skewness issue in the dataset, a binary skewed logit (Scobit) model was found to be superior to a conventional logistic model and subsequently adopted for further analysis. The estimated results showed that 15 variables were identified to be significant in assessing the IR of the roadway tunnels in Shanghai. Finally, the formula for calculating the IR levels of post-crash traffic systems in tunnels was given and would be a helpful tool to mitigate potential trends in crash-related resilience deterioration. The findings of this study have implications for bridging the gap between conventional traffic safety research and system resilience modeling.

Энтропия системного управления безопасностью дорожного движения: методика и практика использования

The safety issues of road transport operation have been relevant for more than 125 years. During this time, the vision of the essence and ideas about the principles and methods of ensuring road safety (traffic safety paradigms) have changed several times in the world scientific community. The purpose of this article is to present to the scientific community a new, developing entropy approach to assessing the quality of traffic safety system management. The need to use entropy approaches is dictated by the awareness of two main circumstances: the extreme variety of forms, composition and, ultimately, the complexity of transport systems, as well as the low effectiveness of using traditional modeling methods in assessing the quality of large and complex systems, which include traffic safety systems. The use of the entropy approach in the field of traffic safety management is very innovative for Russia. Already quite traditional for other spheres of human existence, the methods of entropy assessment of systemic organization are unfamiliar to transport specialists. In this regard, it should be noted that the entropy approach allows solving those tasks in the field of traffic safety that are inaccessible to conventional tools. An example of such tasks can be a quantitative assessment and comparison of the quality of management of regional traffic safety systems. This is especially important for improving the quality of federal traffic safety management, in particular, for improving goal-setting and subsequent financing of the relevant regional traffic safety programs. This is the practical significance of the author’s ideas. This article presents a method for quantifying the Relative entropy Hn of regional traffic safety systems; comparison and explanation of different levels of organization of traffic safety systems in the Orenburg region and the Republic of Tyva; an entropy classification of regional traffic safety systems in Russia by levels of system organization is presented (2021); an attempt was made to philosophically comprehend the results obtained. The results presented in the article are intermediate. The ideology of using the entropy assessment of system organization can be used not only in relation to such an important aspect of the functioning of transport systems as traffic safety, but also to the identification of other system properties, such as efficiency and quality. Key words: road safety, management, quality, system (process) entropy, entropy approach.

Определение длины разгонного пути

The development of locomotive traffic safety systems has led to the fact that it is already possible to move freight trains at the yellow signal of the passing traffic light of most sections at the speed of more than 60 km/h due to the use of virtual coupling technology, in which the calculation of the permissible speed curve is carried out taking into account information about the movement of the train ahead transmitted between locomotives via radio channel. This means that it is possible to reduce the delimiting interval between trains on the stages without reducing the speed. Due to this, in areas with heavy traffic, it is possible to obtain the actual inter-train interval less than the one designed for three-digit auto-blocking, if a corresponding reduction in the interval of passing departure is ensured. The existing algorithms of station automation limit the possibilities of reducing the departure intervals, so there is a need to study the capabilities of stations to implement intervals smaller than was laid down when designing the site. To do this, the simulation of the departure of trains in virtual coupling was carried out. The conditions under which it is necessary to build the acceleration track are determined, and the method for determining its length is also presented.

Intelligent Vehicle-road Integrated Traffic Safety System Based on Beidou

Intelligent Vehicle-road Integrated Traffic Safety System Based on Beidou

A Multi-Level Risk Framework for Driving Safety Assessment Based on Vehicle Trajectory

Few existing research studies have explored the relationship of road section level, local area level and vehicle level risks within the highway traffic safety system, which can be important to the formation of an effective risk event prediction. This paper proposes a framework of multi-level risks described by a set of carefully selected or designed indicators. The interrelationship among these latent multi-level risks and their observable indicators are explored based on vehicle trajectory data using the structural equation model (SEM). The results show that there exists significant positive correlation between the latent risk constructs that each have adequate convergent validity, and it is difficult to completely separate the local traffic level risk from both the road section level risk and vehicle level risk. The local and road level indicators are also found to be of more importance when risk prediction time gets earlier based on feature importance scoring of the LightGBM. The proposed conceptual multi-level indicator based latent risk framework generally fits with the observed results and emphasises the importance of including multi-level indicators for risk event prediction in the future.

Traffic Safety and City Public Transport System: Case Study of Bengaluru, India

Vehicle crashes are a major concern in rapidly growing urban agglomerations. They also have attracted the attention of researchers, academicians, and policy makers. A large body of research literature exists that throws light on the magnitude of this problem and also indicates the interventions required. In a vast majority of Indian cities, buses are the main mode of public transport. An externality of the bus-based public transport system, like any other mode of transport, is the injuries and fatalities arising out of the crashes involving them. Buses are involved in 12-20 percent of fatal crashes in Indian cities. This paper presents an analysis of the fatal crashes that involved public transport buses in Bengaluru, India. The study suggests that low floor buses with mechanical doors and segregated pedestrian and bicycle lanes can have a major impact on reducing fatal crashes of bicycles and pedestrians involving buses.

Vehicle collisions analysis on highways based on multi-user driving simulator and multinomial logistic regression model on US highways in Michigan

Traffic collision on the highway has become a serious issue because they delay the sustainable development of society. Highway accidents on I-69 have one of the highest crash rates in the U.S. in Michigan and a higher fatality rate than average. This study aimed to identify the factors contributing to highway user crashes on I-69 in Flint, Michigan. This study also aims to find the relationship between the change in the speed limit in certain weather conditions and the number of crashes that are likely to occur as a sequence of this change. A multi-user driving simulator is applied in this study with ten driving simulator scenarios. The multinomial logistic regression (MNL) model has been investigated in this study to identify statistically significant factors that contribute to crashes. The analyses indicated that speeding and speed limits during inclement road/weather conditions significantly affected crashes. Most frequent crashes occur during snowy and icy weather conditions and by changing the speed limit during these weather conditions. Therefore, driver speed is suspected to be the most factor that caused the Vehicle crash on I-69. The method of developing Crash modification factors (CMFs) used in this study will help to reduce crashes and improve traffic system safety performance on highways in Michigan.

Simulation of Multimedia Visual Image Motion Track Marking Based on Artificial Bee Colony Algorithm

With the rapid development of electronic technology, network technology, and multimedia processing technology, people pay more and more attention to the surrounding environment. Paying attention to and handling emergencies have also become one of the main points of attention. Through the combination of multimedia and monitoring system, the collected image data are processed and integratedly controlled by the computer platform, and an intelligent monitoring system for traffic road safety can be obtained. Due to the advantages of multimedia visual image motion trajectory identification technology in road traffic safety, it can effectively prevent the chaos and influence caused by humans in chaotic situations, making it widely used. By identifying the motion trajectories of different objects, road emergencies can be effectively prevented and countermeasures can be established. Based on this, this study proposes the artificial bee colony (ABC) algorithm to identify the motion trajectory in the visual image, but the standard ABC algorithm is too slow to converge in the later stage of trajectory recognition. Therefore, this study is based on the standard ABC algorithm. The trajectory recognition simulation shows that the optimized algorithm accelerates the convergence speed and the ability of the global optimal solution in the trajectory recognition process. Then, the optimized ABC algorithm is used to identify the multimedia visual image trajectory. The experiment shows that the average correct rate of feature extraction is also about 98%. The data identification results also show that the optimized ABC algorithm fits the real trajectory better in the trajectory identification. The running time of the algorithm is shorter than the running time of other comparison algorithms, which fully shows the accuracy and superiority of the algorithm in this study.